Merge tag 'irq-core-2020-12-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull irq updates from Thomas Gleixner:
 "This is the second attempt after the first one failed miserably and
  got zapped to unblock the rest of the interrupt related patches.

  A treewide cleanup of interrupt descriptor (ab)use with all sorts of
  racy accesses, inefficient and disfunctional code. The goal is to
  remove the export of irq_to_desc() to prevent these things from
  creeping up again"

* tag 'irq-core-2020-12-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  genirq: Restrict export of irq_to_desc()
  xen/events: Implement irq distribution
  xen/events: Reduce irq_info:: Spurious_cnt storage size
  xen/events: Only force affinity mask for percpu interrupts
  xen/events: Use immediate affinity setting
  xen/events: Remove disfunct affinity spreading
  xen/events: Remove unused bind_evtchn_to_irq_lateeoi()
  net/mlx5: Use effective interrupt affinity
  net/mlx5: Replace irq_to_desc() abuse
  net/mlx4: Use effective interrupt affinity
  net/mlx4: Replace irq_to_desc() abuse
  PCI: mobiveil: Use irq_data_get_irq_chip_data()
  PCI: xilinx-nwl: Use irq_data_get_irq_chip_data()
  NTB/msi: Use irq_has_action()
  mfd: ab8500-debugfs: Remove the racy fiddling with irq_desc
  pinctrl: nomadik: Use irq_has_action()
  drm/i915/pmu: Replace open coded kstat_irqs() copy
  drm/i915/lpe_audio: Remove pointless irq_to_desc() usage
  s390/irq: Use irq_desc_kstat_cpu() in show_msi_interrupt()
  parisc/irq: Use irq_desc_kstat_cpu() in show_interrupts()
  ...

arch/alpha/kernel/sys_jensen.c

@@ -7,7 +7,7 @@
  *
  * Code supporting the Jensen.
  */
-
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/mm.h>

arch/arm/kernel/smp.c

@@ -549,7 +549,7 @@ void show_ipi_list(struct seq_file *p, int prec)
 		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
 
 		seq_printf(p, " %s\n", ipi_types[i]);
 	}

arch/arm64/kernel/smp.c

@@ -811,7 +811,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
 			   prec >= 4 ? " " : "");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
 		seq_printf(p, "      %s\n", ipi_types[i]);
 	}
 

arch/parisc/kernel/irq.c

@@ -216,12 +216,9 @@ int show_interrupts(struct seq_file *p, void *v)
 		if (!action)
 			goto skip;
 		seq_printf(p, "%3d: ", i);
-#ifdef CONFIG_SMP
+
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-#else
-		seq_printf(p, "%10u ", kstat_irqs(i));
-#endif
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(desc, j));
 
 		seq_printf(p, " %14s", irq_desc_get_chip(desc)->name);
 #ifndef PARISC_IRQ_CR16_COUNTS

arch/s390/kernel/irq.c

@@ -124,7 +124,7 @@ static void show_msi_interrupt(struct seq_file *p, int irq)
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	seq_printf(p, "%3d: ", irq);
 	for_each_online_cpu(cpu)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+		seq_printf(p, "%10u ", irq_desc_kstat_cpu(desc, cpu));
 
 	if (desc->irq_data.chip)
 		seq_printf(p, " %8s", desc->irq_data.chip->name);

arch/x86/kernel/topology.c

@@ -25,6 +25,7 @@
  *
  * Send feedback to <colpatch@us.ibm.com>
  */
+#include <linux/interrupt.h>
 #include <linux/nodemask.h>
 #include <linux/export.h>
 #include <linux/mmzone.h>

drivers/gpu/drm/i915/display/intel_lpe_audio.c

@@ -297,13 +297,9 @@ int intel_lpe_audio_init(struct drm_i915_private *dev_priv)
  */
 void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv)
 {
-	struct irq_desc *desc;
-
 	if (!HAS_LPE_AUDIO(dev_priv))
 		return;
 
-	desc = irq_to_desc(dev_priv->lpe_audio.irq);
-
 	lpe_audio_platdev_destroy(dev_priv);
 
 	irq_free_desc(dev_priv->lpe_audio.irq);

drivers/gpu/drm/i915/i915_irq.c

@@ -60,6 +60,24 @@
  * and related files, but that will be described in separate chapters.
  */
 
+/*
+ * Interrupt statistic for PMU. Increments the counter only if the
+ * interrupt originated from the the GPU so interrupts from a device which
+ * shares the interrupt line are not accounted.
+ */
+static inline void pmu_irq_stats(struct drm_i915_private *i915,
+				 irqreturn_t res)
+{
+	if (unlikely(res != IRQ_HANDLED))
+		return;
+
+	/*
+	 * A clever compiler translates that into INC. A not so clever one
+	 * should at least prevent store tearing.
+	 */
+	WRITE_ONCE(i915->pmu.irq_count, i915->pmu.irq_count + 1);
+}
+
 typedef bool (*long_pulse_detect_func)(enum hpd_pin pin, u32 val);
 typedef u32 (*hotplug_enables_func)(struct drm_i915_private *i915,
 				    enum hpd_pin pin);
@@ -1668,6 +1686,8 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 		valleyview_pipestat_irq_handler(dev_priv, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -1745,6 +1765,8 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 		valleyview_pipestat_irq_handler(dev_priv, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -2155,6 +2177,8 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg)
 	if (sde_ier)
 		raw_reg_write(regs, SDEIER, sde_ier);
 
+	pmu_irq_stats(i915, ret);
+
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
 	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 
@@ -2541,6 +2565,8 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 
 	gen8_master_intr_enable(regs);
 
+	pmu_irq_stats(dev_priv, IRQ_HANDLED);
+
 	return IRQ_HANDLED;
 }
 
@@ -2636,6 +2662,8 @@ __gen11_irq_handler(struct drm_i915_private * const i915,
 
 	gen11_gu_misc_irq_handler(gt, gu_misc_iir);
 
+	pmu_irq_stats(i915, IRQ_HANDLED);
+
 	return IRQ_HANDLED;
 }
 
@@ -3934,6 +3962,8 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		i8xx_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -4043,6 +4073,8 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		i915_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -4189,6 +4221,8 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		i965_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, IRQ_HANDLED);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;

drivers/gpu/drm/i915/i915_pmu.c

@@ -4,7 +4,6 @@
  * Copyright © 2017-2018 Intel Corporation
  */
 
-#include <linux/irq.h>
 #include <linux/pm_runtime.h>
 
 #include "gt/intel_engine.h"
@@ -424,22 +423,6 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static u64 count_interrupts(struct drm_i915_private *i915)
-{
-	/* open-coded kstat_irqs() */
-	struct irq_desc *desc = irq_to_desc(i915->drm.pdev->irq);
-	u64 sum = 0;
-	int cpu;
-
-	if (!desc || !desc->kstat_irqs)
-		return 0;
-
-	for_each_possible_cpu(cpu)
-		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
-
-	return sum;
-}
-
 static void i915_pmu_event_destroy(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -590,7 +573,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 				   USEC_PER_SEC /* to MHz */);
 			break;
 		case I915_PMU_INTERRUPTS:
-			val = count_interrupts(i915);
+			val = READ_ONCE(pmu->irq_count);
 			break;
 		case I915_PMU_RC6_RESIDENCY:
 			val = get_rc6(&i915->gt);

drivers/gpu/drm/i915/i915_pmu.h

@@ -111,6 +111,14 @@ struct i915_pmu {
 	 * @sleep_last: Last time GT parked for RC6 estimation.
 	 */
 	ktime_t sleep_last;
+	/**
+	 * @irq_count: Number of interrupts
+	 *
+	 * Intentionally unsigned long to avoid atomics or heuristics on 32bit.
+	 * 4e9 interrupts are a lot and postprocessing can really deal with an
+	 * occasional wraparound easily. It's 32bit after all.
+	 */
+	unsigned long irq_count;
 	/**
 	 * @events_attr_group: Device events attribute group.
 	 */

drivers/mfd/ab8500-debugfs.c

@@ -1513,24 +1513,14 @@ static int ab8500_interrupts_show(struct seq_file *s, void *p)
 {
 	int line;
 
-	seq_puts(s, "name: number:  number of: wake:\n");
+	seq_puts(s, "name: number: irq: number of: wake:\n");
 
 	for (line = 0; line < num_interrupt_lines; line++) {
-		struct irq_desc *desc = irq_to_desc(line + irq_first);
-
-		seq_printf(s, "%3i:  %6i %4i",
+		seq_printf(s, "%3i:  %4i %6i %4i\n",
 			   line,
+			   line + irq_first,
 			   num_interrupts[line],
 			   num_wake_interrupts[line]);
-
-		if (desc && desc->name)
-			seq_printf(s, "-%-8s", desc->name);
-		if (desc && desc->action) {
-			struct irqaction *action = desc->action;
-
-			seq_printf(s, "  %s", action->name);
-			while ((action = action->next) != NULL)
-				seq_printf(s, ", %s", action->name);
 		}
 		seq_putc(s, '\n');
 	}

drivers/net/ethernet/mellanox/mlx4/en_cq.c

@@ -90,7 +90,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 			int cq_idx)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int err = 0;
+	int irq, err = 0;
 	int timestamp_en = 0;
 	bool assigned_eq = false;
 
@@ -116,10 +116,8 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 
 			assigned_eq = true;
 		}
-
-		cq->irq_desc =
-			irq_to_desc(mlx4_eq_get_irq(mdev->dev,
-						    cq->vector));
+		irq = mlx4_eq_get_irq(mdev->dev, cq->vector);
+		cq->aff_mask = irq_get_effective_affinity_mask(irq);
 	} else {
 		/* For TX we use the same irq per
 		ring we assigned for the RX    */

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -958,18 +958,14 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 
 	/* If we used up all the quota - we're probably not done yet... */
 	if (done == budget || !clean_complete) {
-		const struct cpumask *aff;
-		struct irq_data *idata;
 		int cpu_curr;
 
 		/* in case we got here because of !clean_complete */
 		done = budget;
 
 		cpu_curr = smp_processor_id();
-		idata = irq_desc_get_irq_data(cq->irq_desc);
-		aff = irq_data_get_affinity_mask(idata);
 
-		if (likely(cpumask_test_cpu(cpu_curr, aff)))
+		if (likely(cpumask_test_cpu(cpu_curr, cq->aff_mask)))
 			return budget;
 
 		/* Current cpu is not according to smp_irq_affinity -

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -47,6 +47,7 @@
 #endif
 #include <linux/cpu_rmap.h>
 #include <linux/ptp_clock_kernel.h>
+#include <linux/irq.h>
 #include <net/xdp.h>
 
 #include <linux/mlx4/device.h>
@@ -365,7 +366,7 @@ struct mlx4_en_cq {
 	struct mlx4_cqe *buf;
 #define MLX4_EN_OPCODE_ERROR	0x1e
 
-	struct irq_desc *irq_desc;
+	const struct cpumask *aff_mask;
 };
 
 struct mlx4_en_port_profile {

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -684,7 +684,7 @@ struct mlx5e_channel {
 	spinlock_t                 async_icosq_lock;
 
 	/* data path - accessed per napi poll */
-	struct irq_desc *irq_desc;
+	const struct cpumask	  *aff_mask;
 	struct mlx5e_ch_stats     *stats;
 
 	/* control */

drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c

@@ -479,7 +479,6 @@ int mlx5e_port_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
 	c->num_tc   = params->num_tc;
 	c->stats    = &priv->port_ptp_stats.ch;
-	c->irq_desc = irq_to_desc(irq);
 	c->lag_port = lag_port;
 
 	netif_napi_add(netdev, &c->napi, mlx5e_ptp_napi_poll, 64);

drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h

@@ -28,7 +28,6 @@ struct mlx5e_port_ptp {
 	u8                         lag_port;
 
 	/* data path - accessed per napi poll */
-	struct irq_desc *irq_desc;
 	struct mlx5e_ch_stats     *stats;
 
 	/* control */

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -1987,7 +1987,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->num_tc   = params->num_tc;
 	c->xdp      = !!params->xdp_prog;
 	c->stats    = &priv->channel_stats[ix].ch;
-	c->irq_desc = irq_to_desc(irq);
+	c->aff_mask = irq_get_effective_affinity_mask(irq);
 	c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix);
 
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);

drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c

@@ -40,12 +40,8 @@
 static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 {
 	int current_cpu = smp_processor_id();
-	const struct cpumask *aff;
-	struct irq_data *idata;
 
-	idata = irq_desc_get_irq_data(c->irq_desc);
-	aff = irq_data_get_affinity_mask(idata);
-	return cpumask_test_cpu(current_cpu, aff);
+	return cpumask_test_cpu(current_cpu, c->aff_mask);
 }
 
 static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq)

drivers/ntb/msi.c

@@ -282,15 +282,13 @@ int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, irq_handler_t handler,
 				  struct ntb_msi_desc *msi_desc)
 {
 	struct msi_desc *entry;
-	struct irq_desc *desc;
 	int ret;
 
 	if (!ntb->msi)
 		return -EINVAL;
 
 	for_each_pci_msi_entry(entry, ntb->pdev) {
-		desc = irq_to_desc(entry->irq);
-		if (desc->action)
+		if (irq_has_action(entry->irq))
 			continue;
 
 		ret = devm_request_threaded_irq(&ntb->dev, entry->irq, handler,

drivers/pci/controller/mobiveil/pcie-mobiveil-host.c

@@ -306,13 +306,11 @@ int mobiveil_host_init(struct mobiveil_pcie *pcie, bool reinit)
 
 static void mobiveil_mask_intx_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(data->irq);
-	struct mobiveil_pcie *pcie;
+	struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data);
 	struct mobiveil_root_port *rp;
 	unsigned long flags;
 	u32 mask, shifted_val;
 
-	pcie = irq_desc_get_chip_data(desc);
 	rp = &pcie->rp;
 	mask = 1 << ((data->hwirq + PAB_INTX_START) - 1);
 	raw_spin_lock_irqsave(&rp->intx_mask_lock, flags);
@@ -324,13 +322,11 @@ static void mobiveil_mask_intx_irq(struct irq_data *data)
 
 static void mobiveil_unmask_intx_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(data->irq);
-	struct mobiveil_pcie *pcie;
+	struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data);
 	struct mobiveil_root_port *rp;
 	unsigned long flags;
 	u32 shifted_val, mask;
 
-	pcie = irq_desc_get_chip_data(desc);
 	rp = &pcie->rp;
 	mask = 1 << ((data->hwirq + PAB_INTX_START) - 1);
 	raw_spin_lock_irqsave(&rp->intx_mask_lock, flags);

drivers/pci/controller/pcie-xilinx-nwl.c

@@ -374,13 +374,11 @@ static void nwl_pcie_msi_handler_low(struct irq_desc *desc)
 
 static void nwl_mask_leg_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(data->irq);
-	struct nwl_pcie *pcie;
+	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
 	unsigned long flags;
 	u32 mask;
 	u32 val;
 
-	pcie = irq_desc_get_chip_data(desc);
 	mask = 1 << (data->hwirq - 1);
 	raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags);
 	val = nwl_bridge_readl(pcie, MSGF_LEG_MASK);
@@ -390,13 +388,11 @@ static void nwl_mask_leg_irq(struct irq_data *data)
 
 static void nwl_unmask_leg_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(data->irq);
-	struct nwl_pcie *pcie;
+	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
 	unsigned long flags;
 	u32 mask;
 	u32 val;
 
-	pcie = irq_desc_get_chip_data(desc);
 	mask = 1 << (data->hwirq - 1);
 	raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags);
 	val = nwl_bridge_readl(pcie, MSGF_LEG_MASK);

drivers/pinctrl/nomadik/pinctrl-nomadik.c

@@ -948,8 +948,8 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s,
 			   (mode < 0) ? "unknown" : modes[mode]);
 	} else {
 		int irq = chip->to_irq(chip, offset);
-		struct irq_desc	*desc = irq_to_desc(irq);
 		const int pullidx = pull ? 1 : 0;
+		bool wake;
 		int val;
 		static const char * const pulls[] = {
 			"none        ",
@@ -969,8 +969,9 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s,
 		 * This races with request_irq(), set_irq_type(),
 		 * and set_irq_wake() ... but those are "rare".
 		 */
-		if (irq > 0 && desc && desc->action) {
+		if (irq > 0 && irq_has_action(irq)) {
 			char *trigger;
+			bool wake;
 
 			if (nmk_chip->edge_rising & BIT(offset))
 				trigger = "edge-rising";
@@ -979,10 +980,10 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s,
 			else
 				trigger = "edge-undefined";
 
+			wake = !!(nmk_chip->real_wake & BIT(offset));
+
 			seq_printf(s, " irq-%d %s%s",
-				   irq, trigger,
-				   irqd_is_wakeup_set(&desc->irq_data)
-				   ? " wakeup" : "");
+				   irq, trigger, wake ? " wakeup" : "");
 		}
 	}
 	clk_disable(nmk_chip->clk);

drivers/xen/events/events_base.c

@@ -95,7 +95,8 @@ struct irq_info {
 	struct list_head list;
 	struct list_head eoi_list;
 	short refcnt;
-	short spurious_cnt;
+	u8 spurious_cnt;
+	u8 is_accounted;
 	enum xen_irq_type type; /* type */
 	unsigned irq;
 	evtchn_port_t evtchn;   /* event channel */
@@ -161,6 +162,9 @@ static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
 /* IRQ <-> IPI mapping */
 static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
 
+/* Event channel distribution data */
+static atomic_t channels_on_cpu[NR_CPUS];
+
 static int **evtchn_to_irq;
 #ifdef CONFIG_X86
 static unsigned long *pirq_eoi_map;
@@ -257,6 +261,32 @@ static void set_info_for_irq(unsigned int irq, struct irq_info *info)
 		irq_set_chip_data(irq, info);
 }
 
+/* Per CPU channel accounting */
+static void channels_on_cpu_dec(struct irq_info *info)
+{
+	if (!info->is_accounted)
+		return;
+
+	info->is_accounted = 0;
+
+	if (WARN_ON_ONCE(info->cpu >= nr_cpu_ids))
+		return;
+
+	WARN_ON_ONCE(!atomic_add_unless(&channels_on_cpu[info->cpu], -1 , 0));
+}
+
+static void channels_on_cpu_inc(struct irq_info *info)
+{
+	if (WARN_ON_ONCE(info->cpu >= nr_cpu_ids))
+		return;
+
+	if (WARN_ON_ONCE(!atomic_add_unless(&channels_on_cpu[info->cpu], 1,
+					    INT_MAX)))
+		return;
+
+	info->is_accounted = 1;
+}
+
 /* Constructors for packed IRQ information. */
 static int xen_irq_info_common_setup(struct irq_info *info,
 				     unsigned irq,
@@ -339,6 +369,7 @@ static void xen_irq_info_cleanup(struct irq_info *info)
 {
 	set_evtchn_to_irq(info->evtchn, -1);
 	info->evtchn = 0;
+	channels_on_cpu_dec(info);
 }
 
 /*
@@ -433,18 +464,25 @@ static bool pirq_needs_eoi_flag(unsigned irq)
 	return info->u.pirq.flags & PIRQ_NEEDS_EOI;
 }
 
-static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu)
+static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu,
+			       bool force_affinity)
 {
 	int irq = get_evtchn_to_irq(evtchn);
 	struct irq_info *info = info_for_irq(irq);
 
 	BUG_ON(irq == -1);
-#ifdef CONFIG_SMP
+
+	if (IS_ENABLED(CONFIG_SMP) && force_affinity) {
 		cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(cpu));
-#endif
+		cpumask_copy(irq_get_effective_affinity_mask(irq),
+			     cpumask_of(cpu));
+	}
+
 	xen_evtchn_port_bind_to_cpu(evtchn, cpu, info->cpu);
 
+	channels_on_cpu_dec(info);
 	info->cpu = cpu;
+	channels_on_cpu_inc(info);
 }
 
 /**
@@ -523,8 +561,10 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious)
 		return;
 
 	if (spurious) {
-		if ((1 << info->spurious_cnt) < (HZ << 2))
+		if ((1 << info->spurious_cnt) < (HZ << 2)) {
+			if (info->spurious_cnt != 0xFF)
 				info->spurious_cnt++;
+		}
 		if (info->spurious_cnt > 1) {
 			delay = 1 << (info->spurious_cnt - 2);
 			if (delay > HZ)
@@ -615,11 +655,6 @@ static void xen_irq_init(unsigned irq)
 {
 	struct irq_info *info;
 
-#ifdef CONFIG_SMP
-	/* By default all event channels notify CPU#0. */
-	cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(0));
-#endif
-
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (info == NULL)
 		panic("Unable to allocate metadata for IRQ%d\n", irq);
@@ -628,6 +663,11 @@ static void xen_irq_init(unsigned irq)
 	info->refcnt = -1;
 
 	set_info_for_irq(irq, info);
+	/*
+	 * Interrupt affinity setting can be immediate. No point
+	 * in delaying it until an interrupt is handled.
+	 */
+	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 
 	INIT_LIST_HEAD(&info->eoi_list);
 	list_add_tail(&info->list, &xen_irq_list_head);
@@ -739,17 +779,6 @@ static void eoi_pirq(struct irq_data *data)
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	if (unlikely(irqd_is_setaffinity_pending(data)) &&
-	    likely(!irqd_irq_disabled(data))) {
-		int masked = test_and_set_mask(evtchn);
-
-		clear_evtchn(evtchn);
-
-		irq_move_masked_irq(data);
-
-		if (!masked)
-			unmask_evtchn(evtchn);
-	} else
 	clear_evtchn(evtchn);
 
 	if (pirq_needs_eoi(data->irq)) {
@@ -794,7 +823,7 @@ static unsigned int __startup_pirq(unsigned int irq)
 		goto err;
 
 	info->evtchn = evtchn;
-	bind_evtchn_to_cpu(evtchn, 0);
+	bind_evtchn_to_cpu(evtchn, 0, false);
 
 	rc = xen_evtchn_port_setup(evtchn);
 	if (rc)
@@ -1113,8 +1142,14 @@ static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip)
 			irq = ret;
 			goto out;
 		}
-		/* New interdomain events are bound to VCPU 0. */
-		bind_evtchn_to_cpu(evtchn, 0);
+		/*
+		 * New interdomain events are initially bound to vCPU0 This
+		 * is required to setup the event channel in the first
+		 * place and also important for UP guests because the
+		 * affinity setting is not invoked on them so nothing would
+		 * bind the channel.
+		 */
+		bind_evtchn_to_cpu(evtchn, 0, false);
 	} else {
 		struct irq_info *info = info_for_irq(irq);
 		WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
@@ -1132,12 +1167,6 @@ int bind_evtchn_to_irq(evtchn_port_t evtchn)
 }
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
 
-int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn)
-{
-	return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip);
-}
-EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi);
-
 static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
@@ -1168,7 +1197,11 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 			irq = ret;
 			goto out;
 		}
-		bind_evtchn_to_cpu(evtchn, cpu);
+		/*
+		 * Force the affinity mask to the target CPU so proc shows
+		 * the correct target.
+		 */
+		bind_evtchn_to_cpu(evtchn, cpu, true);
 	} else {
 		struct irq_info *info = info_for_irq(irq);
 		WARN_ON(info == NULL || info->type != IRQT_IPI);
@@ -1281,7 +1314,11 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
 			goto out;
 		}
 
-		bind_evtchn_to_cpu(evtchn, cpu);
+		/*
+		 * Force the affinity mask for percpu interrupts so proc
+		 * shows the correct target.
+		 */
+		bind_evtchn_to_cpu(evtchn, cpu, percpu);
 	} else {
 		struct irq_info *info = info_for_irq(irq);
 		WARN_ON(info == NULL || info->type != IRQT_VIRQ);
@@ -1646,9 +1683,7 @@ void rebind_evtchn_irq(evtchn_port_t evtchn, int irq)
 
 	mutex_unlock(&irq_mapping_update_lock);
 
-        bind_evtchn_to_cpu(evtchn, info->cpu);
-	/* This will be deferred until interrupt is processed */
-	irq_set_affinity(irq, cpumask_of(info->cpu));
+	bind_evtchn_to_cpu(evtchn, info->cpu, false);
 
 	/* Unmask the event channel. */
 	enable_irq(irq);
@@ -1682,7 +1717,7 @@ static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
 	 * it, but don't do the xenlinux-level rebind in that case.
 	 */
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
-		bind_evtchn_to_cpu(evtchn, tcpu);
+		bind_evtchn_to_cpu(evtchn, tcpu, false);
 
 	if (!masked)
 		unmask_evtchn(evtchn);
@@ -1690,27 +1725,47 @@ static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
 	return 0;
 }
 
+/*
+ * Find the CPU within @dest mask which has the least number of channels
+ * assigned. This is not precise as the per cpu counts can be modified
+ * concurrently.
+ */
+static unsigned int select_target_cpu(const struct cpumask *dest)
+{
+	unsigned int cpu, best_cpu = UINT_MAX, minch = UINT_MAX;
+
+	for_each_cpu_and(cpu, dest, cpu_online_mask) {
+		unsigned int curch = atomic_read(&channels_on_cpu[cpu]);
+
+		if (curch < minch) {
+			minch = curch;
+			best_cpu = cpu;
+		}
+	}
+
+	/*
+	 * Catch the unlikely case that dest contains no online CPUs. Can't
+	 * recurse.
+	 */
+	if (best_cpu == UINT_MAX)
+		return select_target_cpu(cpu_online_mask);
+
+	return best_cpu;
+}
+
 static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 			    bool force)
 {
-	unsigned tcpu = cpumask_first_and(dest, cpu_online_mask);
-	int ret = xen_rebind_evtchn_to_cpu(evtchn_from_irq(data->irq), tcpu);
+	unsigned int tcpu = select_target_cpu(dest);
+	int ret;
 
+	ret = xen_rebind_evtchn_to_cpu(evtchn_from_irq(data->irq), tcpu);
 	if (!ret)
 		irq_data_update_effective_affinity(data, cpumask_of(tcpu));
 
 	return ret;
 }
 
-/* To be called with desc->lock held. */
-int xen_set_affinity_evtchn(struct irq_desc *desc, unsigned int tcpu)
-{
-	struct irq_data *d = irq_desc_get_irq_data(desc);
-
-	return set_affinity_irq(d, cpumask_of(tcpu), false);
-}
-EXPORT_SYMBOL_GPL(xen_set_affinity_evtchn);
-
 static void enable_dynirq(struct irq_data *data)
 {
 	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
@@ -1734,17 +1789,6 @@ static void ack_dynirq(struct irq_data *data)
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	if (unlikely(irqd_is_setaffinity_pending(data)) &&
-	    likely(!irqd_irq_disabled(data))) {
-		int masked = test_and_set_mask(evtchn);
-
-		clear_evtchn(evtchn);
-
-		irq_move_masked_irq(data);
-
-		if (!masked)
-			unmask_evtchn(evtchn);
-	} else
 	clear_evtchn(evtchn);
 }
 
@@ -1830,7 +1874,8 @@ static void restore_cpu_virqs(unsigned int cpu)
 
 		/* Record the new mapping. */
 		(void)xen_irq_info_virq_setup(cpu, irq, evtchn, virq);
-		bind_evtchn_to_cpu(evtchn, cpu);
+		/* The affinity mask is still valid */
+		bind_evtchn_to_cpu(evtchn, cpu, false);
 	}
 }
 
@@ -1855,7 +1900,8 @@ static void restore_cpu_ipis(unsigned int cpu)
 
 		/* Record the new mapping. */
 		(void)xen_irq_info_ipi_setup(cpu, irq, evtchn, ipi);
-		bind_evtchn_to_cpu(evtchn, cpu);
+		/* The affinity mask is still valid */
+		bind_evtchn_to_cpu(evtchn, cpu, false);
 	}
 }
 
@@ -1938,8 +1984,12 @@ void xen_irq_resume(void)
 	xen_evtchn_resume();
 
 	/* No IRQ <-> event-channel mappings. */
-	list_for_each_entry(info, &xen_irq_list_head, list)
-		info->evtchn = 0; /* zap event-channel binding */
+	list_for_each_entry(info, &xen_irq_list_head, list) {
+		/* Zap event-channel binding */
+		info->evtchn = 0;
+		/* Adjust accounting */
+		channels_on_cpu_dec(info);
+	}
 
 	clear_evtchn_to_irq_all();
 

drivers/xen/evtchn.c

@@ -421,36 +421,6 @@ static void evtchn_unbind_from_user(struct per_user_data *u,
 	del_evtchn(u, evtchn);
 }
 
-static DEFINE_PER_CPU(int, bind_last_selected_cpu);
-
-static void evtchn_bind_interdom_next_vcpu(evtchn_port_t evtchn)
-{
-	unsigned int selected_cpu, irq;
-	struct irq_desc *desc;
-	unsigned long flags;
-
-	irq = irq_from_evtchn(evtchn);
-	desc = irq_to_desc(irq);
-
-	if (!desc)
-		return;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	selected_cpu = this_cpu_read(bind_last_selected_cpu);
-	selected_cpu = cpumask_next_and(selected_cpu,
-			desc->irq_common_data.affinity, cpu_online_mask);
-
-	if (unlikely(selected_cpu >= nr_cpu_ids))
-		selected_cpu = cpumask_first_and(desc->irq_common_data.affinity,
-				cpu_online_mask);
-
-	this_cpu_write(bind_last_selected_cpu, selected_cpu);
-
-	/* unmask expects irqs to be disabled */
-	xen_set_affinity_evtchn(desc, selected_cpu);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
 static long evtchn_ioctl(struct file *file,
 			 unsigned int cmd, unsigned long arg)
 {
@@ -508,10 +478,8 @@ static long evtchn_ioctl(struct file *file,
 			break;
 
 		rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
-		if (rc == 0) {
+		if (rc == 0)
 			rc = bind_interdomain.local_port;
-			evtchn_bind_interdom_next_vcpu(rc);
-		}
 		break;
 	}
 

include/linux/interrupt.h

@@ -232,6 +232,7 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 # define local_irq_enable_in_hardirq()	local_irq_enable()
 #endif
 
+bool irq_has_action(unsigned int irq);
 extern void disable_irq_nosync(unsigned int irq);
 extern bool disable_hardirq(unsigned int irq);
 extern void disable_irq(unsigned int irq);

include/linux/irq.h

@@ -906,6 +906,13 @@ struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d)
 }
 #endif
 
+static inline struct cpumask *irq_get_effective_affinity_mask(unsigned int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+
+	return d ? irq_data_get_effective_affinity_mask(d) : NULL;
+}
+
 unsigned int arch_dynirq_lower_bound(unsigned int from);
 
 int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,

include/linux/irqdesc.h

@@ -113,6 +113,12 @@ static inline void irq_unlock_sparse(void) { }
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
 
+static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc,
+					      unsigned int cpu)
+{
+	return desc->kstat_irqs ? *per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
+}
+
 static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
 {
 	return container_of(data->common, struct irq_desc, irq_common_data);
@@ -179,12 +185,7 @@ int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq,
 /* Test to see if a driver has successfully requested an irq */
 static inline int irq_desc_has_action(struct irq_desc *desc)
 {
-	return desc->action != NULL;
-}
-
-static inline int irq_has_action(unsigned int irq)
-{
-	return irq_desc_has_action(irq_to_desc(irq));
+	return desc && desc->action != NULL;
 }
 
 /**
@@ -228,40 +229,31 @@ irq_set_chip_handler_name_locked(struct irq_data *data, struct irq_chip *chip,
 	data->chip = chip;
 }
 
+bool irq_check_status_bit(unsigned int irq, unsigned int bitmask);
+
 static inline bool irq_balancing_disabled(unsigned int irq)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status_use_accessors & IRQ_NO_BALANCING_MASK;
+	return irq_check_status_bit(irq, IRQ_NO_BALANCING_MASK);
 }
 
 static inline bool irq_is_percpu(unsigned int irq)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status_use_accessors & IRQ_PER_CPU;
+	return irq_check_status_bit(irq, IRQ_PER_CPU);
 }
 
 static inline bool irq_is_percpu_devid(unsigned int irq)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status_use_accessors & IRQ_PER_CPU_DEVID;
+	return irq_check_status_bit(irq, IRQ_PER_CPU_DEVID);
 }
 
+void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
+			     struct lock_class_key *request_class);
 static inline void
 irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
 		      struct lock_class_key *request_class)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (desc) {
-		lockdep_set_class(&desc->lock, lock_class);
-		lockdep_set_class(&desc->request_mutex, request_class);
-	}
+	if (IS_ENABLED(CONFIG_LOCKDEP))
+		__irq_set_lockdep_class(irq, lock_class, request_class);
 }
 
 #endif

include/linux/kernel_stat.h

@@ -67,7 +67,6 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
-extern unsigned int kstat_irqs(unsigned int irq);
 extern unsigned int kstat_irqs_usr(unsigned int irq);
 
 /*

kernel/irq/irqdesc.c

@@ -147,12 +147,12 @@ static ssize_t per_cpu_count_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
-	int cpu, irq = desc->irq_data.irq;
 	ssize_t ret = 0;
 	char *p = "";
+	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		unsigned int c = kstat_irqs_cpu(irq, cpu);
+		unsigned int c = irq_desc_kstat_cpu(desc, cpu);
 
 		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c);
 		p = ",";
@@ -352,7 +352,9 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	return radix_tree_lookup(&irq_desc_tree, irq);
 }
-EXPORT_SYMBOL(irq_to_desc);
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+EXPORT_SYMBOL_GPL(irq_to_desc);
+#endif
 
 static void delete_irq_desc(unsigned int irq)
 {
@@ -924,15 +926,7 @@ static bool irq_is_nmi(struct irq_desc *desc)
 	return desc->istate & IRQS_NMI;
 }
 
-/**
- * kstat_irqs - Get the statistics for an interrupt
- * @irq:	The interrupt number
- *
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. The caller must ensure that the interrupt is not removed
- * concurrently.
- */
-unsigned int kstat_irqs(unsigned int irq)
+static unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned int sum = 0;
@@ -943,21 +937,22 @@ unsigned int kstat_irqs(unsigned int irq)
 	if (!irq_settings_is_per_cpu_devid(desc) &&
 	    !irq_settings_is_per_cpu(desc) &&
 	    !irq_is_nmi(desc))
-	    return desc->tot_count;
+		return data_race(desc->tot_count);
 
 	for_each_possible_cpu(cpu)
-		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
+		sum += data_race(*per_cpu_ptr(desc->kstat_irqs, cpu));
 	return sum;
 }
 
 /**
- * kstat_irqs_usr - Get the statistics for an interrupt
+ * kstat_irqs_usr - Get the statistics for an interrupt from thread context
  * @irq:	The interrupt number
  *
  * Returns the sum of interrupt counts on all cpus since boot for @irq.
- * Contrary to kstat_irqs() this can be called from any context.
- * It uses rcu since a concurrent removal of an interrupt descriptor is
- * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
+ *
+ * It uses rcu to protect the access since a concurrent removal of an
+ * interrupt descriptor is observing an rcu grace period before
+ * delayed_free_desc()/irq_kobj_release().
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
@@ -968,3 +963,17 @@ unsigned int kstat_irqs_usr(unsigned int irq)
 	rcu_read_unlock();
 	return sum;
 }
+
+#ifdef CONFIG_LOCKDEP
+void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
+			     struct lock_class_key *request_class)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc) {
+		lockdep_set_class(&desc->lock, lock_class);
+		lockdep_set_class(&desc->request_mutex, request_class);
+	}
+}
+EXPORT_SYMBOL_GPL(__irq_set_lockdep_class);
+#endif

kernel/irq/manage.c

@@ -2822,3 +2822,40 @@ int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
 	return err;
 }
 EXPORT_SYMBOL_GPL(irq_set_irqchip_state);
+
+/**
+ * irq_has_action - Check whether an interrupt is requested
+ * @irq:	The linux irq number
+ *
+ * Returns: A snapshot of the current state
+ */
+bool irq_has_action(unsigned int irq)
+{
+	bool res;
+
+	rcu_read_lock();
+	res = irq_desc_has_action(irq_to_desc(irq));
+	rcu_read_unlock();
+	return res;
+}
+EXPORT_SYMBOL_GPL(irq_has_action);
+
+/**
+ * irq_check_status_bit - Check whether bits in the irq descriptor status are set
+ * @irq:	The linux irq number
+ * @bitmask:	The bitmask to evaluate
+ *
+ * Returns: True if one of the bits in @bitmask is set
+ */
+bool irq_check_status_bit(unsigned int irq, unsigned int bitmask)
+{
+	struct irq_desc *desc;
+	bool res = false;
+
+	rcu_read_lock();
+	desc = irq_to_desc(irq);
+	if (desc)
+		res = !!(desc->status_use_accessors & bitmask);
+	rcu_read_unlock();
+	return res;
+}

kernel/irq/proc.c

@@ -488,9 +488,10 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (!desc || irq_settings_is_hidden(desc))
 		goto outsparse;
 
-	if (desc->kstat_irqs)
+	if (desc->kstat_irqs) {
 		for_each_online_cpu(j)
-			any_count |= *per_cpu_ptr(desc->kstat_irqs, j);
+			any_count |= data_race(*per_cpu_ptr(desc->kstat_irqs, j));
+	}
 
 	if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
 		goto outsparse;